IBM's Watson Supercomputer Trains Up for Cyber Security

Written by

IBM Security has announced a year-long research project to train the Watson supercomputer for cognitive cybersecurity.

Watson, which has made headlines for artificial intelligence projects and chess matches, will be made smarter in partnership with eight universities in the US and Canada. The collective goal of the project is to address the cybersecurity skills gap while helping train Watson on the nuances of security research findings. It will be tasked with discovering behavior patterns and evidence of hidden cyberattacks and threats that could otherwise be missed—in order to help IT staff better do their day-to-day jobs.

Consider this: today, the volume of security data in front of cybersecurity analysts is staggering. The average organization deals with over 200,000 security events per day, leading to 32 separate potential attacks daily. This chase is leading to even the most well-equipped companies wasting over 21,000 hours and more than a million dollars a year, combing through security events that prove not to be a threat (false positives). And, IBM research shows that today’s security analysts miss over 90% of the security information, but, with Watson, this number will shrink and bring greater speed and precision in their day-to-day work to ultimately achieve a leg up over cybercriminals.

“Even if the industry was able to fill the estimated 1.5 million open cyber security jobs by 2020, we’d still have a skills crisis in security,” said Marc van Zadelhoff, GM, IBM Security. “The volume and velocity of data in security is one of our greatest challenges in dealing with cybercrime. By leveraging Watson’s ability to bring context to staggering amounts of unstructured data, impossible for people alone to process, we will bring new insights, recommendations, and knowledge to security professionals, bringing greater speed and precision to the most advanced cybersecurity analysts, and providing novice analysts with on-the-job training."

IBM plans to aggressively “build the brain” of the Watson system over the next 12 months (at a rate of approximately 15,000 documents per month), so that the next generation of security professionals will no longer be faced with an insurmountable flood of data.

Starting this fall, IBM will work with the universities and their students to further train Watson on the language of cybersecurity, including: California State Polytechnic University, Pomona; Pennsylvania State University; Massachusetts Institute of Technology; New York University; the University of Maryland, Baltimore County (UMBC); the University of New Brunswick; the University of Ottawa and the University of Waterloo.

IBM’s X-Force research library will be a central part of the materials fed to Watson. This body of knowledge includes 20 years of security research, details on 8 million spam and phishing attacks and over 100,000 documented vulnerabilities.

Photo © JuliusKielaitis/Shutterstock.com

What’s hot on Infosecurity Magazine?